Bitte verwenden Sie diesen Link, wenn Sie dieses Dokument zitieren oder verlinken wollen: https://nbn-resolving.org/urn:nbn:de:gbv:9-opus-126648
FRUITS: feature extraction using iterated sums for time series classification
- We introduce a pipeline for time series classification that extracts features based on the iterated-sums signature (ISS) and then applies a linear classifier. These features are intrinsically nonlinear, capture chronological information, and, under certain settings, are invariant to a form of time-warping. We achieve competitive results, both in accuracy and speed, on the UCR archive. We make our code available at https://github.com/irkri/fruits .
Download full text files
Additional Services
| Author: | Joscha Diehl, Richard Krieg |
|---|---|
| URN: | urn:nbn:de:gbv:9-opus-126648 |
| DOI: | https://doi.org/10.1007/s10618-024-01068-1 |
| ISSN: | 1384-5810 |
| ISSN: | 1573-756X |
| Parent Title (English): | Data Mining and Knowledge Discovery |
| Subtitle (English): | FRUITS: feature extraction using... |
| Publisher: | Springer Nature |
| Place of publication: | Berlin |
| Document Type: | Article |
| Language: | English |
| Date of Publication (online): | 2024/09/14 |
| Date of first Publication: | 2024/11/01 |
| Release Date: | 2025/08/29 |
| Tag: | Iterated sums; Time series classification; Tropical semiring |
| Volume: | 38 |
| Issue: | 6 |
| Page Number: | 35 |
| First Page: | 4122 |
| Last Page: | 4156 |
| Faculties: | Mathematisch-Naturwissenschaftliche Fakultät / Institut für Mathematik und Informatik |
| Collections: | weitere DFG-förderfähige Artikel |
| Licence (German): |  Creative Commons - Namensnennung 4.0 International |